Add changes from 3.0.6-2, 3.0.6-3 and several unreleased changes
[privoxy.git] / default.action.master
index f1b4f55..b7dcfc7 100644 (file)
@@ -9,7 +9,7 @@
 # 
 #  File        :  $Source: /cvsroot/ijbswa/current/default.action.master,v $
 # 
-#  $Id: default.action.master,v 1.55 2007/01/20 13:24:29 fabiankeil Exp $
+#  $Id: default.action.master,v 1.76 2007/05/17 15:37:00 fabiankeil Exp $
 #
 #  Requires    :  This version requires Privoxy v3.0.7 or later due to 
 #                 syntax changes.
 #    Block this URL. Privoxy will ignore this URL completely, and not request
 #    it.
 #
+# +client-header-filter{name}
+#    All client headers to which this action applies are filtered on-the-fly
+#    through the specified regular expression based substitutions.
+#
+#    Client-header filters predefined in the supplied default.filter include:
+#
+#     hide-tor-exit-notation: Removes the Tor exit node notation in Host and Referer headers
+#
 # +content-type-overwrite
 #    Replaces the "Content-Type:" HTTP server header, so that unwanted
 #    download menus will not pop up, or changes the browser's rendering mode.
 #    be seen with View Source), not the headers. Repeat for multiple filters.
 #    Use with caution: filters can be very intrusive.
 #   
-#    Filters predefined in the supplied default.action include:
+#    Filters predefined in the supplied default.filter include:
 #
 #     js-annoyances:         Get rid of particularly annoying JavaScript abuse
 #     js-events:             Kill all JS event bindings (Radically destructive! Use only on real suckers)
 #     yahoo:                 Removes text ads and other Yahoo specific improvements
 #     msn:                   Removes text ads and other MSN specific improvements
 #     blogspot:              Cleans up Blogspot blogs
-#     html-to-xml:           Header filter to change the Content-Type from html to xml
-#     xml-to-html:           Header filter to change the Content-Type from xml to html
 #     no-ping:               Removes non-standard ping attributes from anchor and area tags
-#     hide-tor-exit-notation: Header filter to remove the Tor exit node notation in Host and Referer headers
-#
-# +filter-client-headers
-#    By default, filters only apply to the document content itself. This will
-#    extend those filters to include the client's headers as well.
-#
-# +filter-server-headers
-#    By default, filters only apply to the document content itself. This will
-#    extend those filters to include the server's headers as well.
 #
 # +force-text-mode
 #    Declares a document as plain text, even if the "Content-Type:" isn't detected 
 # +inspect-jpegs
 #    Scan jpeg headers for malformed comment blocks and correct them.
 #
-# +set-image-blocker{blank}
-# +set-image-blocker{pattern}
-# +set-image-blocker{<URL>} with <url> being any valid image URL
-#    Decides what to do with URLs that end up tagged with {+block +handle-as-image}.
-#    There are 4 options:
-#      * "-set-image-blocker" will send a HTML "blocked" page, usually
-#         resulting in a "broken image" icon.
-#      * "+set-image-blocker{blank}" will send a 1x1 transparent image
-#      * "+set-image-blocker{pattern}" will send a 4x4 grey/white pattern
-#        which is less intrusive than the logo but easier to recognize
-#        than the transparent one.
-#      * "+set-image-blocker{<URL>}" will send a HTTP temporary redirect
-#        to the specified image URL.
-#
-#
 # +limit-connect{portlist}
 #   The CONNECT methods exists in HTTP to allow access to secure websites
 #   (https:// URLs) through proxies. It works very simply: The proxy
 #   connects to the server on the specified port, and then short-circuits
-#   its connections to the cliant and to the remote proxy.
+#   its connections to the client and to the remote proxy.
 #   This can be a big security hole, since CONNECT-enabled proxies can
 #   be abused as TCP relays very easily.
 #   By default, i.e. in the absence of a +limit-connect action, Privoxy
 #    and +gif-deanimate will not work on compressed data. Will slow down
 #    connections to those websites, though.
 #
-# +prevent-keeping-cookies
+# +server-header-filter{name}
+#    All server headers to which this action applies are filtered on-the-fly
+#    through the specified regular expression based substitutions.
+#
+#    Server-header filters predefined in the supplied default.filter include:
+#
+#     html-to-xml:           Changes the Content-Type header from html to xml
+#     xml-to-html:           Changes the Content-Type header from xml to html
+#
 # +session-cookies-only
 #    If the website sets cookies, make sure they are erased when you exit
 #    and restart your web browser.  This makes profiling cookies useless,
 #    but won't break sites which require cookies so that you can log in
 #    or for transactions.
 #
+# +set-image-blocker{blank}
+# +set-image-blocker{pattern}
+# +set-image-blocker{<URL>} with <url> being any valid image URL
+#    Decides what to do with URLs that end up tagged with {+block +handle-as-image}.
+#    There are 4 options:
+#      * "-set-image-blocker" will send a HTML "blocked" page, usually
+#         resulting in a "broken image" icon.
+#      * "+set-image-blocker{blank}" will send a 1x1 transparent image
+#      * "+set-image-blocker{pattern}" will send a 4x4 grey/white pattern
+#        which is less intrusive than the logo but easier to recognize
+#        than the transparent one.
+#      * "+set-image-blocker{<URL>}" will send a HTTP temporary redirect
+#        to the specified image URL.
+#
+#
 # +crunch-outgoing-cookies
 #    Prevent the website from reading cookies
 #
 #    equivalent.
 #
 # +redirect{<URL>}
+# +redirect{<pcrs command>}
 #    Convinces the browser that the requested document has been moved to
 #    another location and the browser should get it from the specified
 #    URL.
@@ -536,6 +542,7 @@ allow-ads   = -block -filter{banners-by-size} -filter{banners-by-link}
 { \
 -add-header \
 -block \
+-client-header-filter{hide-tor-exit-notation} \
 -content-type-overwrite \
 -crunch-client-header \
 -crunch-if-none-match \
@@ -570,12 +577,7 @@ allow-ads   = -block -filter{banners-by-size} -filter{banners-by-link}
 -filter{yahoo} \
 -filter{msn} \
 -filter{blogspot} \
--filter{xml-to-html} \
--filter{html-to-xml} \
 -filter{no-ping} \
--filter{hide-tor-exit-notation} \
--filter-client-headers \
--filter-server-headers \
 -force-text-mode \
 -handle-as-empty-document \
 -handle-as-image \
@@ -594,6 +596,8 @@ allow-ads   = -block -filter{banners-by-size} -filter{banners-by-link}
 -redirect \
 -send-vanilla-wafer \
 -send-wafer \
+-server-header-filter{xml-to-html} \
+-server-header-filter{html-to-xml} \
 -session-cookies-only \
 +set-image-blocker{pattern} \
 -treat-forbidden-connects-like-blocks \
@@ -673,7 +677,7 @@ countr*.
 #############################################################################
 {-block}
 #MASTER# DONT-VERIFY (generic)
-/.*ad(sl|v(i[cs]|o|an|ertencia|ent|.*search)) # advice/advisories/advan*/advertencia (spanish)
+/.*ad(sl|v(i[cs]|o|an|ertencia|ent|.*search|erse)) # advice/advisories/advan*/advertencia (spanish) adverse
 /.*(lo|thre|he|d|gr|l|ro|re|squ|class(ified)?)ads
 /.*account
 support./(.*/)?track
@@ -804,6 +808,16 @@ ad.theadhost.com
 #MASTER# REMARKS: Action tracker 1616457. Added 2007-01-20.
 .topnemo.com/engine
 .top100categories.com/engine
+#MASTER# REMARKS: Actionsfile feedback item #1647852 2007-01-30
+#MASTER# REMARKS: Domain squatting onload pop-ups
+#MASTER# BLOCK-REFERRER: http://www.memtest.com/
+/(t|search)\.php\?uid=ws[a-z0-9]+\.[a-z0-9]+
+MASTER# BLOCK-REFERRER: via Yahoo groups
+MASTER# REMARKS: Actionsfile tracker 1645513 2007-01-26
+.adinterax.com/(?!(.*)\.(js|gif|jpg))
+MASTER# BLOCK-REFERRER:  http://www.weilpod.com
+MASTER# REMARKS: Actionsfile feedback item #1710951 2007-05-02
+img.bluehost.com
 
 #----------------------------------------------------------------------------
 # Misc Web-bugs, JS and just plain Junk. Images here aren't normal images.
@@ -890,6 +904,17 @@ pagead*.googlesyndication./.*\.js
 /js/slider\.js
 #MASTER# BLOCK-REFERRER: http://www.earthcore.com/ feedback item #1605385 12/14/06
 /t\.php\?cat=.*&kw=.*&sc=
+#MASTER# BLOCK-REFERRER: http://floodle.net 2007-01-21 SF tracker
+scripts.chitika.net/.*\.js
+#MASTER# REMARKS: Actionsfile tracker #1674363 2007-03-05, text ads
+#MASTER# BLOCK-REFERRER: http://www.securityfocus.com/archive/1/461489/30/0/threaded
+jlinks.industrybrains.com/
+MASTER# BLOCK-REFERRER: via Yahoo groups
+MASTER# REMARKS: Actionsfile tracker 1645513 2007-01-26
+.adinterax.com/.*\.js
+#MASTER# BLOCK-REFERRER: http://dictionary.reference.com/search?q=privacy&db=*
+MASTER# REMARKS: Actionsfile tracker 1650798 2007-02-02
+.googleadservices.com/gampad/.*\.js
 
 #############################################################################
 # Generic block-as-image patterns:
@@ -934,11 +959,13 @@ pagead*.googlesyndication./.*\.js
 #MASTER# BLOCK-REFERRER: http://www.joecartoon.com/  10/17/06
 .*servedby.advertising.com
 #MASTER# BLOCK-REFERRER: http://www.yahoo.com/
-.a.yimg.com/(?:(?!/i/).)*$
-.a[0-9].yimg.com/(?:(?!/i/).)*$
-.yimg.com/(.*/)?a/
-.yimg.com/.*/(flash|java)/promotions
-.yimg.com/a/.*/flash/
+#.a.yimg.com/(?:(?!/i/).)*$
+#.a[0-9].yimg.com/(?:(?!/i/).)*$
+#.yimg.com/(.*/)?a/
+#.yimg.com/.*/(flash|java)/promotions
+#.yimg.com/a/.*/flash/
+#MASTER# REMARKS: The above replaced with below. Actions file tracker #1645616 2007-01-27
+.yimg.com/.*\.yimg\.com/a/
 #MASTER# DONT-VERIFY
 bs*.gsanet.com
 bs*.einets.com
@@ -948,6 +975,7 @@ bs*.einets.com
 #MASTER# BLOCK-REFERRER: http://maps.yahoo.com/
 #MASTER# REMARKS: Banner farms; just exclude their corp. info
 [a-vx-z]*.atdmt.com/
+view.atdmt.com/
 #MASTER# BLOCK-REFERRER: http://www.exactaudiocopy.de/ 09/11/06
 #MASTER# BLOCK-REFERRER: http://stanford.facebook.com/home.php 
 .fastclick.net
@@ -986,7 +1014,8 @@ jmcms.cydoor.com/
 #MASTER# BLOCK-REFERRER: http://discussion.brighthand.com/forumdisplay.php?s=fee44a5b2a6fc2e9e79d6472bc8fbe94&forumid=197 10/19/06
 *[0-9].tribalfusion.com/
 #MASTER# REMARKS: Actions file tracker 1547656 09/02/06
-img.mediaplex.com
+#MASTER# REMARKS: Update pattern: Actionsfile feedback item #1698822, was opened at 2007-04-11 to catch https://secure.img-cdn.mediaplex.com/0....
+img*.mediaplex.com
 #MASTER# BLOCK-REFERRER: http://www.tomshardware.com/ 09/28/06
 #MASTER# REMARKS: There is adfarm and altfarm.mediaplex
 a*farm.mediaplex.com
@@ -1027,7 +1056,16 @@ searchportal.information.com/
 images.ibsys.com/
 #MASTER# BLOCK-REFERRER: http://www.rentalhouses.com/search_results.php?searchnew=1&citys_city=&citys_county=&citys_state=&ssubmit=Search&Szip=40205&keyword=&listingid=&strs_state=&strs_city=&strs_street= 11/05/06
 .lduhtrp.net/image
-
+#MASTER# BLOCK-REFERRER: http://floodle.net 2007-01-21 SF tracker
+scripts.chitika.net/.*\.(gif|png|jpg)
+#MASTER# REMARKS: Actionsfile feedback item #1648478 2007-01-30
+.projectwonderful.com/gen.php
+#MASTER# BLOCK-REFERRER: http://www.multimap.com/ (sporadic)
+#MASTER# REMARKS: Actionsfile feedback item #1665682 2007-02-21
+.akamai.net/.*\.adtech\.de/.*\.(gif|png)
+MASTER# BLOCK-REFERRER: via Yahoo groups
+MASTER# REMARKS: Actionsfile tracker 1645513 2007-01-26
+.adinterax.com/.*\.(gif|jpg)
 
 #----------------------------------------------------------------------------
 # Cross-site user tracking
@@ -1042,8 +1080,9 @@ statse.webtrendslive.com
 spinbox.versiontracker.com/.*\.(gif|jpg)
 #MASTER# BLOCK-REFERRER: http://mycroft.mozdev.org/ 10/07/06
 stat.onestat.com
-#MASTER# BLOCK-REFERRER: http://www.global.net.uk/ 10/07/06
-.[a-vx-z]*.tradedoubler.com
+#MASTER# BLOCK-REFERRER: http://www.meparecebien.com/noticias/discograficas/sinnamon-records/sinnamon-records-libera-a-sus-artistas-nacionales-para-el-mercado-digital-401/
+#MASTER# REMARKS: Actionsfile feedback item #1644583 2007-03-05
+imp*.tradedoubler.com
 #MASTER# BLOCK-REFERRER: http://www.sharepoint.boo.pl/
 #MASTER# REMARKS: Not found, but left 10/07/06
 stat.webmedia.
@@ -1088,12 +1127,24 @@ tra*.mybloglog.com
 #MASTER# BLOCK-REFERRER:  http://www.polymervision.com/ 
 #MASTER# REMARKS: Actionsfile feedback item #1629370 01/16/07
 .guesttrace.
+#MASTER# BLOCK-REFERRER: http://dictionary.com
+#MASTER# REMARKS: Actionsfile feedback item #165078 2007-02-05
+insightxe./data/
+#MASTER# BLOCK-REFERRER:  http://www.unitedairlines.com
+#MASTER# REMARKS: Actionsfile feedback item #1650797 2007-02-05
+.insightfirst.com
+#MASTER# BLOCK-REFERRER: http://rss.slashdot.org/Slashdot/slashdot
+#MASTER# PROBLEM URL: rss.slashdot.org/~a/Slashdot/slashdot?i=ofbWqX
+rss.slashdot.org/~a/Slashdot/slashdot\?
+#MASTER# PROBLEM URL: rss.slashdot.org/~r/Slashdot/slashdot/~4/102113044
+rss.slashdot.org/~r/Slashdot/slashdot/~4/
 
 #----------------------------------------------------------------------------
 # Specific counters (see above for generic patterns)
 #----------------------------------------------------------------------------
 #MASTER# BLOCK-REFERRER: http://www.distrowatch.com/table.php?distribution=linex 10/19/06
-s*.sitemeter.com/meter
+#MASTER# BLOCK-REFERRER: http://floodle.net 2007-01-21 tracker  #1641102
+s*.sitemeter.com/(meter|js/counter.js)
 #MASTER# BLOCK-REFERRER: http://personales.mundivia.es/lbouza/ 10/19/06
 fastcounter.bcentral.com/
 #MASTER# BLOCK-REFERRER: http://osnews.com/ 10/19/06
@@ -1290,6 +1341,30 @@ edge.macworld.com
 .parcel2go.com/track
 #MASTER# REMARKS: Actionsfile Tracker #1612950 12/11/06
 .amazon.com/gp/gift-central/.*recip/
+#MASTER# UNBLOCK-REFERRER: http://yahoo.com 2007-01-27
+#MASTER# REMARKS: Actionsfile Tracker #1645501, this is a UI page element.
+.yimg.com/.*/themes/ad/
+#MASTER# UNBLOCK-REFERRER: http://mozilla.hongo.wide.ad.jp/pub/mozilla.org//thunderbird/releases/
+#MASTER# REMARKS: Actionsfile feedback item #1672918 2007-03-03
+.ad.*/pub/mozilla.org/
+#MASTER# UNBLOCK-REFERRER: http://lads.myspace.com/mini/mini.swf?b=NDgwNzU1ODE=&o=NjQwNzIzMA==&d=MTE3NDI4ODcwNg==&i=MA==&a=VHJ1ZQ==
+#MASTER# UNBLOCK-REFERRER: http://profile.myspace.com/index.cfm?fuseaction=user.viewprofile&friendid=5282733
+#MASTER# UNBLOCK-REFERRER: http://lads.myspace.com/videos/vplayer.swf
+#MASTER# REMARKS: MySpace videos caught by .*ads. The above profile.myspace.com link grabs the vplayer.swf file (which does not work when directly fetched)
+lads.myspace.com
+#MASTER# REMARKS: 20070402 Adam Piggott first-party tracking. 20070411 Moved from generic unblockers by path to site-specific unblockers.
+#MASTER# UNBLOCK-REFERRER: http://www.shockwave.com/servlet/DownloadEcommTracker?sku=fizzball-pc&promoCode=SiteShockwaveLandingPage
+.shockwave.com/servlet/DownloadEcommTracker
+#MASTER# UNBLOCK-REFERRER: http://www.fish4.co.uk/iad/lettings/advert?adId=12389712&src=nestoria
+#MASTER# REMARKS 20070411 Adam Piggott fish4.co.uk is a popular UK advertising site for cars, properties and jobs and uses ad/advert all over the place, understandably.
+.fish4.co.uk/.*ad
+#MASTER# REMARKS Actionsfile feedback item #1700037 2007-04-13 HB
+#MASTER# UNBLOCK-REFERRER: http://www.mp3.com.au/popup/popup.asp?id=110433
+.mp3.com.au/.*popup
+#MASTER# REMARKS Actionsfile feedback #1700915 2007-04-15
+#MASTER# UNBLOCK-REFERRER: http://www.svd.se/ego/339/http://www.e24.se/dynamiskt/reklam_media/did_15092793.asp
+#MASTER# UNBLOCK-REFERRER: http://www.e24.se/dynamiskt/reklam_media/did_15092793.asp
+/(.*/)?dynamiskt/reklam_media/did_
 
 #############################################################################
 # Site-specific special rules:
@@ -1429,6 +1504,12 @@ www.translate.ru/url/
 schneegans.de/
 #MASTER# PROBLEM-URL: http://config.privoxy.org/edit-actions-submit?f=user ... &redirect_mode=http%3A%2F%2Fwww.privoxy.org%2F
 config.privoxy.org/
+#MASTER# PROBLEM-URL: http://users.wsj.com/lmda/do/checkLogin?mg=evo-wsj&url=http%3A%2F%2Fonline.wsj.com%2Farticle%2FSB117313867582027623.html
+.wsj.com/lmda/do/checkLogin
+#MASTER# PROBLEM-URL: http://del.icio.us/url/check\?url=http%3A%2F%2Fwww.privoxy.org
+#MASTER# REMARKS: As we already have five other PROBLEM-URLs that contain '?url=',
+#MASTER# REMARKS: it might make sense to allow '/.*?url=' in general
+del.icio.us/
 
 #----------------------------------------------------------------------------
 # No filtering for sourcecode or other automatically parsed content
@@ -1779,6 +1860,13 @@ www.skweezer.net/bloglines
 {+redirect{http://config.privoxy.org/}}
 .privoxy.org/config
 
+#MASTER# REMARKS: Privoxy's "unsafe" CGI pages check the referrer 
+#MASTER# REMARKS: to make sure the user reached them intentionally.
+#MASTER# REMARKS: If the referrer is blocked, CGI editing is impossible.
+{-hide-referrer}
+p.p/
+config.privoxy.org/
+
 #MASTER# REMARKS: Yahoo logout URLs need special treatment,
 #MASTER# REMARKS: the URL after "done=" is no fast-redirect. 2007-01-19 fk
 #MASTER# REMARKS: Reported in support request #1635354.
@@ -1787,3 +1875,24 @@ www.skweezer.net/bloglines
 .yahoo./.*http://login.yahoo.com/config/login.*http://
 
 #MASTER# set vi:nowrap
+
+#----------------------------------------------------------------------------
+# Sections that modify the action settings based on tags.
+#----------------------------------------------------------------------------
+
+#############################################################################
+# Depends on +client-header-tagger{image-requests}
+#############################################################################
+{-handle-as-empty-document \
+ +handle-as-image \
+}
+TAG:^IMAGE-REQUEST$
+
+#############################################################################
+# Depends on +client-header-tagger{css-requests}
+#############################################################################
+{+handle-as-empty-document \
+ -handle-as-image \
+}
+TAG:^CSS-REQUEST$
+